Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    many

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ACTIONS
    -0.07
    936
    -0.06
     carts
    -0.06
     тем
    -0.06
    _surf
    -0.06
    outcome
    -0.06
    slaught
    -0.06
     Kirst
    -0.06
    ReturnValue
    -0.06
    获
    -0.06
    POSITIVE LOGITS
     many
    0.10
     percentage
    0.07
     долго
    0.07
     Many
    0.07
     viele
    0.07
     labyrinth
    0.06
     Investors
    0.06
     дозвол
    0.06
     JSONArray
    0.06
    isma
    0.06
    Act Density 0.051%

    No Known Activations